arXiv subjects

Gabriel Appleby

Publications and source records attributed to Gabriel Appleby.

13 recordsLinked to original sources

arXiv2025

The Role of Visualization in LLM-Assisted Knowledge Graph Systems: Effects on User Trust, Exploration, and Workflows

Knowledge graphs (KGs) are powerful data structures, but exploring them effectively remains difficult for even expert users. Large language models (LLMs) are increasingly used to address this gap, yet little is known empirically about how their usage with KGs shapes user trust, exploration strategies, or downstream decision-making - raising key design challenges for LLM-based KG visual analysis systems. To study these effects, we developed LinkQ, a KG exploration system that converts natural language questions into structured queries with an LLM. We collaborated with KG experts to design five visual mechanisms that help users assess the accuracy of both KG queries and LLM responses: an LLM-KG state diagram that illustrates which stage of the exploration pipeline LinkQ is in, a query editor displaying the generated query paired with an LLM explanation, an entity-relation ID table showing extracted KG entities and relations with semantic descriptions, a query structure graph that depicts the path traversed in the KG, and an interactive graph visualization of query results. From a qualitative evaluation with 14 practitioners, we found that users - even KG experts - tended to overtrust LinkQ's outputs due to its "helpful" visualizations, even when the LLM was incorrect. Users exhibited distinct workflows depending on their prior familiarity with KGs and LLMs, challenging the assumption that these systems are one-size-fits-all - despite often being designed as if they are. Our findings highlight the risks of false trust in LLM-assisted data analysis tools and the need for further investigation into the role of visualization as a mitigation technique.

cs.LG↗

arXiv2025

Mitigating LLM Hallucinations with Knowledge Graphs: A Case Study

High-stakes domains like cyber operations need responsible and trustworthy AI methods. While large language models (LLMs) are becoming increasingly popular in these domains, they still suffer from hallucinations. This research paper provides learning outcomes from a case study with LinkQ, an open-source natural language interface that was developed to combat hallucinations by forcing an LLM to query a knowledge graph (KG) for ground-truth data during question-answering (QA). We conduct a quantitative evaluation of LinkQ using a well-known KGQA dataset, showing that the system outperforms GPT-4 but still struggles with certain question categories - suggesting that alternative query construction strategies will need to be investigated in future LLM querying systems. We discuss a qualitative study of LinkQ with two domain experts using a real-world cybersecurity KG, outlining these experts' feedback, suggestions, perceived limitations, and future opportunities for systems like LinkQ.

cs.HC↗

arXiv2024

LinkQ: An LLM-Assisted Visual Interface for Knowledge Graph Question-Answering

We present LinkQ, a system that leverages a large language model (LLM) to facilitate knowledge graph (KG) query construction through natural language question-answering. Traditional approaches often require detailed knowledge of a graph querying language, limiting the ability for users -- even experts -- to acquire valuable insights from KGs. LinkQ simplifies this process by implementing a multistep protocol in which the LLM interprets a user's question, then systematically converts it into a well-formed query. LinkQ helps users iteratively refine any open-ended questions into precise ones, supporting both targeted and exploratory analysis. Further, LinkQ guards against the LLM hallucinating outputs by ensuring users' questions are only ever answered from ground truth KG data. We demonstrate the efficacy of LinkQ through a qualitative study with five KG practitioners. Our results indicate that practitioners find LinkQ effective for KG question-answering, and desire future LLM-assisted exploratory data analysis systems.

cs.CL↗

arXiv2024

A Typology of Decision-Making Tasks for Visualization

Despite decision-making being a vital goal of data visualization, little work has been done to differentiate decision-making tasks within the field. While visualization task taxonomies and typologies exist, they often focus on more granular analytical tasks that are too low-level to describe large complex decisions, which can make it difficult to reason about and design decision-support tools. In this paper, we contribute a typology of decision-making tasks that were iteratively refined from a list of design goals distilled from a literature review. Our typology is concise and consists of only three tasks: CHOOSE, ACTIVATE, and CREATE. Although decision types originating in other disciplines exist, we provide definitions for these tasks that are suitable for the visualization community. Our proposed typology offers two benefits. First, the ability to compose and hierarchically organize the tasks enables flexible and clear descriptions of decisions with varying levels of complexities. Second, the typology encourages productive discourse between visualization designers and domain experts by abstracting the intricacies of data, thereby promoting clarity and rigorous analysis of decision-making processes. We demonstrate the benefits of our typology through four case studies, and present an evaluation of the typology from semi-structured interviews with experienced members of the visualization community who have contributed to developing or publishing decision support systems for domain experts. Our interviewees used our typology to delineate the decision-making processes supported by their systems, demonstrating its descriptive capacity and effectiveness. Finally, we present preliminary findings on the usefulness of our typology for visualization design.

cs.HC↗

arXiv2024

DimBridge: Interactive Explanation of Visual Patterns in Dimensionality Reductions with Predicate Logic

Dimensionality reduction techniques are widely used for visualizing high-dimensional data. However, support for interpreting patterns of dimension reduction results in the context of the original data space is often insufficient. Consequently, users may struggle to extract insights from the projections. In this paper, we introduce DimBridge, a visual analytics tool that allows users to interact with visual patterns in a projection and retrieve corresponding data patterns. DimBridge supports several interactions, allowing users to perform various analyses, from contrasting multiple clusters to explaining complex latent structures. Leveraging first-order predicate logic, DimBridge identifies subspaces in the original dimensions relevant to a queried pattern and provides an interface for users to visualize and interact with them. We demonstrate how DimBridge can help users overcome the challenges associated with interpreting visual patterns in projections.

cs.HC↗

arXiv2024

A Preliminary Roadmap for LLMs as Assistants in Exploring, Analyzing, and Visualizing Knowledge Graphs

We present a mixed-methods study to explore how large language models (LLMs) can assist users in the visual exploration and analysis of knowledge graphs (KGs). We surveyed and interviewed 20 professionals from industry, government laboratories, and academia who regularly work with KGs and LLMs, either collaboratively or concurrently. Our findings show that participants overwhelmingly want an LLM to facilitate data retrieval from KGs through joint query construction, to identify interesting relationships in the KG through multi-turn conversation, and to create on-demand visualizations from the KG that enhance their trust in the LLM's outputs. To interact with an LLM, participants strongly prefer a chat-based 'widget,' built on top of their regular analysis workflows, with the ability to guide the LLM using their interactions with a visualization. When viewing an LLM's outputs, participants similarly prefer a combination of annotated visuals (e.g., subgraphs or tables extracted from the KG) alongside summarizing text. However, participants also expressed concerns about an LLM's ability to maintain semantic intent when translating natural language questions into KG queries, the risk of an LLM 'hallucinating' false data from the KG, and the difficulties of engineering a 'perfect prompt.' From the analysis of our interviews, we contribute a preliminary roadmap for the design of LLM-driven knowledge graph exploration systems and outline future opportunities in this emergent design space.

cs.HC↗

arXiv2023

RekomGNN: Visualizing, Contextualizing and Evaluating Graph Neural Networks Recommendations

Content recommendation tasks increasingly use Graph Neural Networks, but it remains challenging for machine learning experts to assess the quality of their outputs. Visualization systems for GNNs that could support this interrogation are few. Moreover, those that do exist focus primarily on exposing GNN architectures for tuning and prediction tasks and do not address the challenges of recommendation tasks. We developed RekomGNN, a visual analytics system that supports ML experts in exploring GNN recommendations across several dimensions and making annotations about their quality. RekomGNN straddles the design space between Neural Network and recommender system visualization to arrive at a set of encoding and interaction choices for recommendation tasks. We found that RekomGNN helps experts make qualitative assessments of the GNN's results, which they can use for model refinement. Overall, our contributions and findings add to the growing understanding of visualizing GNNs for increasingly complex tasks.

cs.HC↗

arXiv2023

Kriging Convolutional Networks

Spatial interpolation is a class of estimation problems where locations with known values are used to estimate values at other locations, with an emphasis on harnessing spatial locality and trends. Traditional Kriging methods have strong Gaussian assumptions, and as a result, often fail to capture complexities within the data. Inspired by the recent progress of graph neural networks, we introduce Kriging Convolutional Networks (KCN), a method of combining the advantages of Graph Convolutional Networks (GCN) and Kriging. Compared to standard GCNs, KCNs make direct use of neighboring observations when generating predictions. KCNs also contain the Kriging method as a specific configuration. We further improve the model's performance by adding attention. Empirically, we show that this model outperforms GCNs and Kriging in several applications. The implementation of KCN using PyTorch is publicized at the GitHub repository: https://github.com/tufts-ml/kcn-torch.

cs.LG↗

arXiv2023

Knowledge Graphs in Practice: Characterizing their Users, Challenges, and Visualization Opportunities

This study presents insights from interviews with nineteen Knowledge Graph (KG) practitioners who work in both enterprise and academic settings on a wide variety of use cases. Through this study, we identify critical challenges experienced by KG practitioners when creating, exploring, and analyzing KGs that could be alleviated through visualization design. Our findings reveal three major personas among KG practitioners - KG Builders, Analysts, and Consumers - each of whom have their own distinct expertise and needs. We discover that KG Builders would benefit from schema enforcers, while KG Analysts need customizable query builders that provide interim query results. For KG Consumers, we identify a lack of efficacy for node-link diagrams, and the need for tailored domain-specific visualizations to promote KG adoption and comprehension. Lastly, we find that implementing KGs effectively in practice requires both technical and social solutions that are not addressed with current tools, technologies, and collaborative workflows. From the analysis of our interviews, we distill several visualization research directions to improve KG usability, including knowledge cards that balance digestibility and discoverability, timeline views to track temporal changes, interfaces that support organic discovery, and semantic explanations for AI and machine learning predictions.

cs.HC↗

arXiv2022

Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Paper

Research papers, in addition to textual documents, are a designed interface through which researchers communicate. Recently, rapid growth has transformed that interface in many fields of computing. In this work, we examine the effects of this growth from a media archaeology perspective, through the changes to figures and tables in research papers. Specifically, we study these changes in computer vision over the past decade, as the deep learning revolution has driven unprecedented growth in the discipline. We ground our investigation through interviews with veteran researchers spanning computer vision, graphics, and visualization. Our analysis focuses on the research attention economy: how research paper elements contribute towards advertising, measuring, and disseminating an increasingly commodified "contribution." Through this work, we seek to motivate future discussion surrounding the design of both the research paper itself as well as the larger sociotechnical research publishing system, including tools for finding, reading, and writing research papers.

cs.CY↗

arXiv2022

Are Metrics Enough? Guidelines for Communicating and Visualizing Predictive Models to Subject Matter Experts

Presenting a predictive model's performance is a communication bottleneck that threatens collaborations between data scientists and subject matter experts. Accuracy and error metrics alone fail to tell the whole story of a model - its risks, strengths, and limitations - making it difficult for subject matter experts to feel confident in their decision to use a model. As a result, models may fail in unexpected ways or go entirely unused, as subject matter experts disregard poorly presented models in favor of familiar, yet arguably substandard methods. In this paper, we describe an iterative study conducted with both subject matter experts and data scientists to understand the gaps in communication between these two groups. We find that, while the two groups share common goals of understanding the data and predictions of the model, friction can stem from unfamiliar terms, metrics, and visualizations - limiting the transfer of knowledge to SMEs and discouraging clarifying questions being asked during presentations. Based on our findings, we derive a set of communication guidelines that use visualization as a common medium for communicating the strengths and weaknesses of a model. We provide a demonstration of our guidelines in a regression modeling scenario and elicit feedback on their use from subject matter experts. From our demonstration, subject matter experts were more comfortable discussing a model's performance, more aware of the trade-offs for the presented model, and better equipped to assess the model's risks - ultimately informing and contextualizing the model's use beyond text and numbers.

cs.HC↗

arXiv2021

UnProjection: Leveraging Inverse-Projections for Visual Analytics of High-Dimensional Data

Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Although many such methods exist, comparably little work has been done on generalizable methods of inverse-projection -- the process of mapping the projected points, or more generally, the projection space back to the original high-dimensional space. In this paper we present NNInv, a deep learning technique with the ability to approximate the inverse of any projection or mapping. NNInv learns to reconstruct high-dimensional data from any arbitrary point on a 2D projection space, giving users the ability to interact with the learned high-dimensional representation in a visual analytics system. We provide an analysis of the parameter space of NNInv, and offer guidance in selecting these parameters. We extend validation of the effectiveness of NNInv through a series of quantitative and qualitative analyses. We then demonstrate the method's utility by applying it to three visualization tasks: interactive instance interpolation, classifier agreement, and gradient visualization.

cs.HC↗

arXiv2021

HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters

Projection algorithms such as t-SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperparameters which must be tuned carefully. Unfortunately, iteratively recomputing projections to find the optimal hyperparameter value is computationally intensive and unintuitive due to the stochastic nature of these methods. In this paper we propose HyperNP, a scalable method that allows for real-time interactive hyperparameter exploration of projection methods by training neural network approximations. HyperNP can be trained on a fraction of the total data instances and hyperparameter configurations and can compute projections for new data and hyperparameters at interactive speeds. HyperNP is compact in size and fast to compute, thus allowing it to be embedded in lightweight visualization systems such as web browsers. We evaluate the performance of the HyperNP across three datasets in terms of performance and speed. The results suggest that HyperNP is accurate, scalable, interactive, and appropriate for use in real-world settings.

cs.LG↗